基于遗传蜂群算法的运动想象BCI系统导联选择

Channel selection for motor imagery brain-computer interfaces based on generic bee colony algorithm

针对运动想象脑—机接口系统中,高密度导联导致实验准备时间长、系统运行速度慢、性能变差等问题,提出了一种新的导联优选算法——遗传蜂群算法。该算法通过引入遗传算法的交叉和变异算子以提高蜂群算法的邻域搜索能力,避免陷入局部最优解的问题。对第四届国际BCI竞赛dataset 1中四名被试者(a、b、f和g)的59导联运动想象数据进行导联优选,用多类CSP算法和支持向量机对优选导联数据进行特征提取和分类识别。结果表明,所提出算法在大大降低了导联维数的同时,也得到了比全导联更高的分类识别率,验证了所提算法的实用性和有效性。

In motor imagery brain-computer interfaces systems,high-density multi-channels are often used to acquire electroencephalogram （EEG）.However,excessive channels can lead to some problems,such as long preparation time,slow running speed and poor performance.To address the questions,the paper proposed an improved artificial bee colony algorithm based on genetic operators （GA-ABC）,which was a new algorithm to select the best channels.The algorithm introduced crossover and mutation operators of genetic algorithms to improve the neighborhood search ability of the bee colony algorithm, and to avoid the local optimization of the bee colony algorithm.It used the algorithm to optimize the 59 leads of the subjects a,b,f and g of BCI competition IV dataset 1,and used the multiclass CSP algorithm and support vector machine for feature extraction and classification of EEG.The results show that the proposed algorithm can greatly reduce the number of channels and lead to a higher accuracy,which verifies the practicability and effectiveness of the proposed algorithm.